Graph and Question Interaction Aware Graph2Seq Model for Knowledge Base Question Generation

The Knowledge Base Question Generation (KBQG) is an essential natural language processing task. Taking knowledge graph and answer entities as input, KBQG aims to generate corresponding natural language question. Recently Graph2Seq has been proposed to encode the knowledge graph and achieved remarkable results, while one important challenge still remains, i.e., the graph encoding lacks the interaction with the target question. To deal with the above challenge, we propose a graph and question interaction enhanced Graph2Seq model, in which we design an encoder-decoder parallel enhancement mechanism and apply the knowledge distillation for both inter-mediate representation and prediction distribution to employ the knowledge of the target question into the graph representation. Experiments have been conducted on KBQG benchmark dataset and experimental results have shown the promising potential of proposed method.

I. Introduction

Question Generation (QG) is designed to generate related questions based on the input data [1]. When the input data is in the form of Knowledge Graph (KG), the task is normally called Knowledge Base Question Generation (KBQG), which requires the combination of knowledge representation and Natural Language Generation (NLG) techniques [2]. The intelligent chatbot can also be more proactive by employing KBQG technique to raise questions [3]. Therefore, KBQG has attracted a surge of interests in the recent years.